version: "3.9"

services:
  tts-service:
    build:
      context: .
      dockerfile: Dockerfile
    container_name: silero-tts-service
    restart: unless-stopped
    ports:
      - "8000:8000"
    environment:
      - MODEL=v5_ru
      - DEVICE=cuda:0
      - SAMPLE_RATE=48000
      - TORCH_THREADS=0
      - JIT_COMPILE=false
      - MAX_QUEUE_SIZE=20
      - PROMETHEUS_ENABLED=false
      - LOG_LEVEL=INFO
    volumes:
      - ./models:/app/models:rw
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: 1
              capabilities: [gpu]
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:8000/health"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 120s
    logging:
      driver: "json-file"
      options:
        max-size: "10m"
        max-file: "3"